相关论文: Bootstrap State Representation using Style Transfe…

Recent advances in reinforcement-learning research have demonstrated impressive results in building algorithms that can out-perform humans in complex tasks. Nevertheless, creating reinforcement-learning systems that can build abstractions…

Meta-learning enables rapid generalization to new tasks by learning knowledge from various tasks. It is intuitively assumed that as the training progresses, a model will acquire richer knowledge, leading to better generalization…

Artistic style transfer aims to transfer the style of an artwork to a photograph while maintaining its original overall content. Many prior works focus on designing various transfer modules to transfer the style statistics to the content…

Adaptation of pretrained vision-language models such as CLIP to various downstream tasks have raised great interest in recent researches. Previous works have proposed a variety of test-time adaptation (TTA) methods to achieve strong…

Traditionally, reinforcement learning (RL) agents learn to solve new tasks by updating their neural network parameters through interactions with the task environment. However, recent works demonstrate that some RL agents, after certain…

Deep clustering which adopts deep neural networks to obtain optimal representations for clustering has been widely studied recently. In this paper, we propose a novel deep image clustering framework to learn a category-style latent…

Agents trained via deep reinforcement learning (RL) routinely fail to generalize to unseen environments, even when these share the same underlying dynamics as the training levels. Understanding the generalization properties of RL is one of…

Transfer learning in reinforcement learning (RL) seeks to accelerate learning in new tasks by leveraging knowledge from related sources. Existing neurosymbolic transfer methods, however, typically rely on manually specified task automata,…

Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets. Transfer learning is a potential solution but their effectiveness in the text domain is not as explored as in areas such…

In this paper, we investigate how model distillation impacts the development of reasoning features in large language models (LLMs). To explore this, we train a crosscoder on Qwen-series models and their fine-tuned variants. Our results…

''Grokking'' is a phenomenon where a neural network first memorizes training data and generalizes poorly, but then suddenly transitions to near-perfect generalization after prolonged training. While intriguing, this delayed generalization…

Domain adaptation refers to the process of learning prediction models in a target domain by making use of data from a source domain. Many classic methods solve the domain adaptation problem by establishing a common latent space, which may…

In the field of legged robot motion control, reinforcement learning (RL) holds great promise but faces two major challenges: high computational cost for training individual robots and poor generalization of trained models. To address these…

In this work, we tackle the challenging problem of arbitrary image style transfer using a novel style feature representation learning method. A suitable style representation, as a key component in image stylization tasks, is essential to…

The ability to infer the intentions of others, predict their goals, and deduce their plans are critical features for intelligent agents. For a long time, several approaches investigated the use of symbolic representations and inferences…

Recent work applying deep reinforcement learning (DRL) to solve traveling salesman problems (TSP) has shown that DRL-based solvers can be fast and competitive with TSP heuristics for small instances, but do not generalize well to larger…

The generalization gap in reinforcement learning (RL) has been a significant obstacle that prevents the RL agent from learning general skills and adapting to varying environments. Increasing the generalization capacity of the RL systems can…

Modern reinforcement learning (RL) systems have demonstrated remarkable capabilities in complex environments, such as video games. However, they still fall short of achieving human-like sample efficiency and adaptability when learning new…

Transfer learning promises to reduce the high sample complexity of deep reinforcement learning (RL), yet existing methods struggle with domain shift between source and target environments. Policy distillation provides powerful tactical…

The success of Reinforcement Learning (RL) heavily relies on the ability to learn robust representations from the observations of the environment. In most cases, the representations learned purely by the reinforcement learning loss can…